Conceptio
›
software-architecture
Topic
software-architecture
Knowledge-graph topic
· documents ABOUT software-architecture across the archive
2,242
Documents about software-architecture
Documents about software-architecture
SmartEval: A Benchmark for Evaluating LLM-Generated Smart Contracts from Natural Language Specifications
#175336
arXiv CS
ParityFuzz: Finding Inconsistencies across Solidity Compilers via Fine-Grained Mutation and Differential Analysis
#175346
arXiv CS
Method-level Change-proneness: A Better Metric for Black-box Test Suite Minimization
#195560
arXiv CS
Automated Root-Cause Subclassification and No-Code Fix Generation for Invalid Bug Reports
#200557
arXiv CS
SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering
#200561
arXiv CS
Beyond Execution: Static-Analysis Rewards and Hint-Conditioned Diffusion RL for Code Generation
#200574
arXiv CS
"Refactoring Runaway": Understanding and Mitigating Tangled Refactorings in Coding Agents for Issue Resolution
#216884
arXiv CS
PITMuS: A Tool for Automated Bug Dataset Generation via Source-Level Mutant Reconstruction
#216893
arXiv CS
Evidence Absence Is Not Evidence Insufficiency: Diagnosing NEI Construction Artifacts in Fact Verification
#229566
arXiv CS
Names Are All You Need: Effective and Safe Regression Test Selection for Python
#229585
arXiv CS
Agora: Toward Autonomous Bug Detection in Production-Level Consensus Protocols with LLM Agents
#241560
arXiv CS
Code-QA-Bench: Separating Code Reasoning from Documentation Memorization in Repository-Level QA
#241570
arXiv CS
LLM Based Web Accessibility Repair: An Empirical Study of Detection, Remediation, and Cost
#241586
arXiv CS
OptiLoop: Coordination-in-the-Loop Verification and Repair for LLM-Generated Optimization Agents
#241587
arXiv CS
Asuka-Bench: Benchmarking Code Agents on Underspecified User Intent and Multi-Round Refinement
#259539
arXiv CS
Description-Code Inconsistency in Real-world MCP Servers: Measurement, Detection, and Security Implications
#259563
arXiv CS
A Causal Probabilistic Framework for Perception-Informed Closed-Loop Simulation of Autonomous Driving
#266240
arXiv CS
When LLMs Invent Rust Crates: An Empirical Study of Hallucination Patterns and Mitigation
#267727
arXiv CS
Mining Architectural Quality Under Agentic AI Adoption: A Causal Study of Java Repositories
#271912
arXiv CS
Finding Compiler-Platform Interaction Bugs in Deep Learning Pipelines via Cross-Layer Constraints
#287198
arXiv CS
Beyond Static Endpoints: Tool Programs as an Interface for Flexible Agentic Web Services
#290645
arXiv CS
FUNDAMENTALS OF DESIGNING SOFTWARE FOR LANGUAGE CORPORA
#122142
DataCite
FUNDAMENTALS OF DESIGNING SOFTWARE FOR LANGUAGE CORPORA
#122143
DataCite
Long-Range Correlation in Code Commit Dynamics as a Novel Indicator of Software Product Stability: A Detrended Fluctuation Analysis Study
#155364
arXiv CS
Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering
#2665
arXiv CS
An Empirical Study on Influence-Based Pretraining Data Selection for Code Large Language Models
#2681
arXiv CS
From OSS to Open Source AI: an Exploratory Study of Collaborative Development Paradigm Divergence
#6033
arXiv CS
An Eye for Trust: An Exploration of Developers' Trust Perceptions Through Urgency and Reputation
#6037
arXiv CS
Automated BPMN Model Generation from Textual Process Descriptions: A Multi-Stage LLM-Driven Approach
#13174
arXiv CS
Structured Safety Auditing for Balancing Code Correctness and Content Safety in LLM-Generated Code
#13175
arXiv CS
Vibe-Coding: Feedback-Based Automated Verification with no Human Code Inspection, a Feasibility Study
#19076
arXiv CS
Towards Better Static Code Analysis Reports: Sentence Transformer-based Filtering of Non-Actionable Alerts
#120572
arXiv CS
Cache-Related Smells in GitLab CI/CD: Comprehensive Catalog, Automated Detection, and Empirical Evidence
#120585
arXiv CS
From Language to Action: Enhancing LLM Task Efficiency with Task-Aware MCP Server Recommendation
#120604
arXiv CS
BONSAI: A Mixed-Initiative Workspace for Human-AI Co-Development of Visual Analytics Applications
#124133
arXiv CS
From Particles to Perils: SVGD-Based Hazardous Scenario Generation for Autonomous Driving Systems Testing
#124139
arXiv CS
SpecSyn: LLM-based Synthesis and Refinement of Formal Specifications for Real-world Program Verification
#126584
arXiv CS
mcdok at SemEval-2026 Task 13: Finetuning LLMs for Detection of Machine-Generated Code
#126589
arXiv CS
UniAda: Universal Adaptive Multi-objective Adversarial Attack for End-to-End Autonomous Driving Systems
#139017
arXiv CS
AI as Consumer and Participant: A Co-Design Agenda for MBSE Substrates and Methodology
#141557
arXiv CS
Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora
#141572
arXiv CS
Mitigating False Positives in Static Memory Safety Analysis of Rust Programs via Reinforcement Learning
#155356
arXiv CS
How Compliant Are GitHub Actions Workflows? A Checklist-Based Study with LLM-Assisted Auditing
#155399
arXiv CS
Correct Code, Vulnerable Dependencies: A Large Scale Measurement Study of LLM-Specified Library Versions
#168376
arXiv CS
MAS-Algorithm: A Workflow for Solving Algorithmic Programming Problems with a Multi-Agent System
#168385
arXiv CS
AICoFe: Implementation and Deployment of an AI-Based Collaborative Feedback System for Higher Education
#168401
arXiv CS
Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code
#168405
arXiv CS
AuditRepairBench: A Paired-Execution Trace Corpus for Evaluator-Channel Ranking Instability in Agent Repair
#168408
arXiv CS
When Context Hurts: The Crossover Effect of Knowledge Transfer on Multi-Agent Design Exploration
#168414
arXiv CS
Beyond Autonomy: A Dynamic Tiered AgentRunner Framework for Governable and Resilient Enterprise AI Execution
#175326
arXiv CS
← Previous
Page 16 of 20
Next →
Topic record
· derived from the Conceptio knowledge graph (shared subject terms across the corpus)
Conceptio Open Knowledge Archive — topic hubs link to canonical document pages with full provenance.